摘要
针对雷达辐射源个体识别中特征提取困难和低信噪比下识别率低的问题,从图像角度出发提出了一种基于变分自编码器的雷达辐射源个体识别算法。基于信号时频分析,利用变分自编码器(variational auto-encoder,VAE)提取时频图像的深层特征,并采用核主成分分析(kernel principal component analysis,KPCA)获取特征中的主成分,最后将特征送入支持向量机进行分类识别。仿真结果表明:文中所提算法在识别效率和抗噪声性能等方面均优于其他传统算法。当信噪比(signal-to-noise ratio,SNR)为0 dB时针对6个辐射源进行识别,可获得93%以上的识别率。该算法特征提取简单、系统实时性高,具有较高的工程应用价值。
Aiming at the difficulty of feature extraction and low recognition rate under low signal-to-noise ratio(SNR)in radar emitter individual recognition,this paper proposes a radar emitter individual recognition algorithm based on variational auto-encoder(VAE)from the image point of view.Based on the signal time-frequency analysis,this algorithm extracts the deep features of time-frequency image by using variational self-encoder,and uses kernel principal component analysis(KPCA)to obtain the principal components of the features.Finally,the features are sent to the support vector machine for classification and recognition.The simulation results show that the proposed algorithm is superior to other traditional algorithms in recognition efficiency and anti-noise performance.When the signal-to-noise ratio(SNR)is 0 dB,more than 93%recognition rate can be obtained for six emitters.The algorithm is of simple extraction,high real-time system,and has high engineering application value.
作者
高鹏成
焦淑红
GAO Pengcheng;JIAO Shuhong(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)
出处
《应用科技》
CAS
2020年第4期59-65,共7页
Applied Science and Technology
基金
总装预研重点基金项目(61404150101).
关键词
雷达辐射源识别
时频变换
变分自编码器
核PCA
支持向量机
特征提取
图像预处理
数据降维
radar emitter recognition
time-frequency transformation
VAE
KPCA
support vector machine
feature extraction
image preprocessing
data dimensionality reduction
